# Mengimpor library
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Mengimpor dataset
dataset = pd.read_csv('Pengunjung_mall.csv')
X = dataset.iloc[:, [3, 4]].values

# Menggunakan dendrogram untuk menentukan angka cluster yang tepat
import scipy.cluster.hierarchy as sch
dendrogram = sch.dendrogram(sch.linkage(X, method = 'ward'))
plt.title('Dendrogram')
plt.xlabel('Consumer')
plt.ylabel('Euclidean Distance')
plt.show()

# Menjalankan Hierarchical Clustering ke dataset
from sklearn.cluster import AgglomerativeClustering
hc = AgglomerativeClustering(n_clusters = 3, affinity = 'euclidean', linkage = 'ward')
y_hc = hc.fit_predict(X)

# Visualisasi hasil clusters
plt.scatter(X[y_hc == 0, 0], X[y_hc == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X[y_hc == 1, 0], X[y_hc == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(X[y_hc == 2, 0], X[y_hc == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(X[y_hc == 3, 0], X[y_hc == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
plt.scatter(X[y_hc == 4, 0], X[y_hc == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
plt.title('Consumers Cluster')
plt.xlabel('Yearly Salary')
plt.ylabel('Yearly expense rating (1-100)')
plt.legend()
plt.show()